Research on safe driving behavior of transportation vehicles based on vehicle network data mining
- 24 October 2019
- journal article
- research article
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 31 (5)
Abstract
In recent years, with the rapid development of China's economy and the growth of people's travel demand, road transport industry has developed rapidly. However, at the same time, the traffic safety problems caused by the accelerated growth of transport vehicles are becoming more and more serious. Driver's driving behavior is closely related to traffic safety. With the help of data mining technology, we can make full use of the system data collected by road transportation industry to identify the bad driving behavior of transport vehicles and get seven secondary indicators of traffic safety evaluation indicators: overspeed, accelerated, decelerated, fatigue driving, idle preheating, overspeed idling, and flameout taxiing. According to the indicators, the occurrence times and duration are further subdivided into 14 three‐level indicators. Then, by using the analytic hierarchy process, through the construction of comparison judgment matrix and consistency checking, the corresponding weight of each evaluation index is determined with the help of the entropy method, and the formation safety of transport vehicles is evaluated. The results show that drivers with more fatigue driving, acceleration, and deceleration have higher driving risk. Transportation enterprises and relevant departments need to focus on their monitoring. The combination of data mining, data analysis algorithm, and traffic safety field in machine learning provides a demonstration for the study of safe driving behavior of transport vehicles in China and has a guiding significance for the supervision and training of drivers' driving behavior and reducing road safety risks.Keywords
This publication has 19 references indexed in Scilit:
- Leveraging longitudinal driving behaviour data with data mining techniques for driving style analysisIET Intelligent Transport Systems, 2015
- Driver Behavior Analysis for Safe Driving: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2015
- Recognizing human actions by two-level Beta process hidden Markov modelMultimedia Systems, 2015
- Mimetic finite difference methodJournal of Computational Physics, 2014
- Injury protection and accident causation parameters for vulnerable road users based on German In-Depth Accident Study GIDASAccident Analysis & Prevention, 2012
- Driver Intention Recognition Method Using Continuous Hidden Markov ModelInternational Journal of Computational Intelligence Systems, 2011
- Aberrant driving behaviors: A study of drivers in BeijingAccident Analysis & Prevention, 2010
- Optimal fuzzy control system using the cross-entropy method. A case study of a drilling processInformation Sciences, 2010
- Road safety risk evaluation by means of ordered weighted averaging operators and expert knowledgeKnowledge-Based Systems, 2010
- Towards a general theory of driver behaviourAccident Analysis & Prevention, 2005